activity
20202024
most citedCHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings

97 citations · 135 across the 22 of their papers we have counts for

collaborators

21 papers

eess.AS2024

Robust Audiovisual Speech Recognition Models with Mixture-of-Experts

Yihan Wu, Yifan Peng, Yichen Lu +3

Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech rec…

eess.AS2024

SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data

Yichen Lu, Jiaqi Song, Xuankai Chang +3

In this work, we present SynesLM, an unified model which can perform three multimodal language understanding tasks: audio-visual automatic speech recognition(AV-ASR) and visual-aid…

cs.CL2024

Towards Robust Speech Representation Learning for Thousands of Languages

William Chen, Wangyou Zhang, Yifan Peng +7

Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the worl…

eess.AS2024

LV-CTC: Non-autoregressive ASR with CTC and latent variable models

Yuya Fujita, Shinji Watanabe, Xuankai Chang +1

Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of…

cs.CL2023

Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data

Yifan Peng, Jinchuan Tian, Brian Yan +13

Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech dat…

cs.SD2023

HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model

Takashi Maekaku, Jiatong Shi, Xuankai Chang +2

Recently, the usefulness of self-supervised representation learning (SSRL) methods has been confirmed in various downstream tasks. Many of these models, as exemplified by HuBERT an…